Research and improvement of movie recommendation based on a collaborative filtering algorithm

Abstract

Among various recommendation algorithms, collaborative filtering stands out as a popular and effective technique that analyzes user behavior to suggest personalized items. The goal of studying recommendation algorithms is to enhance the exactness of recommendation outcomes and provide users with tailored suggestions. In this paper, the algorithm of collaborative filtering is divided into User-CF and Item-CF, and their algorithm principles and implementation steps are introduced. The similarity calculation of both methods is improved, and a comparison of their advantages and disadvantages is conducted. Experiments are conducted on the MovieLens-latest-small movie dataset to compare the performance of User-CF and Item-CF before and after their similarity calculation is improved. The results show that the similarity improvement of User-CF can substantially enhance the algorithms inclusiveness, while the similarity improvement of Item-CF does not have a considerable impact on the algorithms performance indicators. Finally, the comparison shows that Item-CF has better coverage and popularity, while User-CF has better precision and recall.